ft_wav2vec2_base_six_500

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2609
• Wer: 45.1739
• Cer: 21.0426

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0001
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2000
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
4.3484	11.36	500	2.9679	98.7617	98.9968
2.4169	22.73	1000	1.2648	64.7328	28.2059
0.6152	34.09	1500	1.1641	47.3113	21.7501
0.2786	45.45	2000	1.2609	45.1739	21.0426

Framework versions

• Transformers 4.39.3
• Pytorch 1.12.1+cu116
• Datasets 2.18.0
• Tokenizers 0.15.2